Unverified50% confidenceFactExact time
A recent study found that large language models do not consistently follow Bayesian rules, and their probabilistic beliefs exhibit internal inconsistencies.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLarge language models are fundamentally probabilistic and cannot guarantee 100% output correctness.80% similarUnverifiedLarge language models have inherent non-determinism — even with identical prompt inputs, the model may return results that differ in format, content, or even logic at different times.79% similarUnverified大语言模型本质上是概率性的，相同的输入可能产生不同的输出，这与传统软件的确定性行为截然不同78% similarUnverifiedText generated by large language models tends to have low perplexity, with word choices that are overly consistent with probabilistic expectations, lacking the unexpectedness of human writing.76% similarUnverifiedCurrent large language models lack real-world perception interfaces and causal reasoning capabilities, and are essentially doing pattern matching rather than intent understanding76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/897396API
curl https://kongchang.com/api/v1/knowledge/claims/897396MCP
get_claim(id=897396)